© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162322
    Prev
    Next
    INDEX
    Explanations

    Technical/Code/Foreign Language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     permanent
    -0.25
     bond
    -0.25
     isot
    -0.25
    ement
    -0.25
    æ´ģ
    -0.24
    inkel
    -0.24
     ground
    -0.24
    rec
    -0.24
    istar
    -0.23
     related
    -0.23
    POSITIVE LOGITS
    å¿ĥè·³
    0.30
    éĥ½éľĢè¦ģ
    0.27
    éĥ½è®¤ä¸º
    0.27
    yling
    0.26
    .getState
    0.26
    _UID
    0.25
     besoin
    0.25
    upo
    0.25
     Isles
    0.24
     Scoped
    0.24
    Activations Density 0.001%

    No Known Activations